Zhide Hu

Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression.

Support vector machines (SVMs) were used to develop QSAR models that correlate molecular structures to their toxicity and bioactivities. The performance and predictive ability of SVM are investigated and compared with other methods such as multiple linear regression and radial basis function neural network methods. In the present study, two different data sets were evaluated. The first one involves an application of SVM to the development of a QSAR model for the prediction of toxicities of 153 phenols, and the second investigation deals with the QSAR model between the structures and the activities of a set of 85 cyclooxygenase 2 (COX-2) inhibitors. For each application, the molecular structures were described using either the physicochemical parameters or molecular descriptors. In both studied cases, the predictive ability of the SVM model is comparable or superior to those obtained by MLR and RBFNN. The results indicate that SVM can be used as an alternative powerful modeling tool for QSAR studies.

Diagnosing breast cancer based on support vector machines.

The Support Vector Machine (SVM) classification algorithm, recently developed from the machine learning community, was used to diagnose breast cancer. At the same time, the SVM was compared to several machine learning techniques currently used in this field. The classification task involves predicting the state of diseases, using data obtained from the UCI machine learning repository. SVM outperformed k-means cluster and two artificial neural networks on the whole. It can be concluded that nine samples could be mislabeled from the comparison of several machine learning techniques.

Radial basis function neural network-based QSPR for the prediction of critical temperature

Abstract A QSPR study was performed to develop models that relate the structures of 856 organic compounds to their critical temperatures. Molecular descriptors derived solely from structure were used to represent molecular structures. A subset of the calculated descriptors selected using forward stepwise regression was used in the QSPR models development. Multiple linear regression (MLR) and radial basis function neural networks (RBFNNs) are utilized to construct the linear and nonlinear QSPR models, respectively. The optimal QSPR model was developed based on a 10–33–1 radial basis function neural network architecture using molecular descriptors calculated from molecular structure alone. The root mean square errors in critical temperature predictions were 13.97 K for the whole set, 12.32 K for the training set, and 14.23 K for the prediction set. The prediction results are in good agreement with the experimental value.

Prediction of the Isoelectric Point of an Amino Acid Based on GA-PLS and SVMs

The support vector machine (SVM), as a novel type of a learning machine, for the first time, was used to develop a QSPR model that relates the structures of 35 amino acids to their isoelectric point. Molecular descriptors calculated from the structure alone were used to represent molecular structures. The seven descriptors selected using GA-PLS, which is a sophisticated hybrid approach that combines GA as a powerful optimization method with PLS as a robust statistical method for variable selection, were used as inputs of RBFNNs and SVM to predict the isoelectric point of an amino acid. The optimal QSPR model developed was based on support vector machines, which showed the following results: the root-mean-square error of 0.2383 and the prediction correlation coefficient R=0.9702 were obtained for the whole data set. Satisfactory results indicated that the GA-PLS approach is a very effective method for variable selection, and the support vector machine is a very promising tool for the nonlinear approximation.

QSAR Models for the Prediction of Binding Affinities to Human Serum Albumin Using the Heuristic Method and a Support Vector Machine

The binding affinities to human serum albumin for 94 diverse drugs and drug-like compounds were modeled with the descriptors calculated from the molecular structure alone using a quantitative structure-activity relationship (QSAR) technique. The heuristic method (HM) and support vector machine (SVM) were utilized to construct the linear and nonlinear prediction models, leading to a good correlation coefficient (R2) of 0.86 and 0.94 and root-mean-square errors (rms) of 0.212 and 0.134 albumin drug binding affinity units, respectively. Furthermore, the models were evaluated by a 10 compound external test set, yielding R2 of 0.71 and 0.89 and rms error of 0.430 and 0.222. The specific information described by the heuristic linear model could give some insights into the factors that are likely to govern the binding affinity of the compounds and be used as an aid to the drug design process; however, the prediction results of the nonlinear SVM model seem to be better than that of the HM.

QSAR study of ethyl 2-[(3-methyl-2,5-dioxo(3-pyrrolinyl))amino]-4-(trifluoromethyl) pyrimidine-5-carboxylate: an inhibitor of AP-1 and NF-kappa B mediated gene expression based on support vector machines.

The support vector machine, as a novel type of learning machine, for the first time, was used to develop a QSAR model of 57 analogues of ethyl 2-[(3-methyl-2,5-dioxo(3-pyrrolinyl))amino]-4-(trifluoromethyl)pyrimidine-5-carboxylate (EPC), an inhibitor of AP-1 and NF-kappa B mediated gene expression, based on calculated quantum chemical parameters. The quantum chemical parameters involved in the model are Kier and Hall index (order3) (KHI3), Information content (order 0) (IC0), YZ Shadow (YZS) and Max partial charge for an N atom (MaxPCN), Min partial charge for an N atom (MinPCN). The mean relative error of the training set, the validation set, and the testing set is 1.35%, 1.52%, and 2.23%, respectively, and the maximum relative error is less than 5.00%.

A study of the interaction between a new reagent and serum albumin by fluorescence spectroscopy

Abstract The synthesis of a new reagent, saturated fatty hydrocarbon substituting group compound N-n-hexyl-N ′-(sodium p-aminobenzenesulfonate) thiourea (HXPT), is described. The interactions between HXPT and bovine serum albumin or human serum albumin were studied by fluorescence spectroscopy. The binding constants of HXPT with BSA or HSA were determined at different temperatures under the optimum conditions. The binding sites were obtained and the acting force were suggested to be mainly hydrophobic. The effect of common ions on the binding constants was also investigated. A practical method was proposed for the determination of HXPT in bovine serum or human serum samples.

Quantification of glutathione and glutathione disulfide in human plasma and tobacco leaves by capillary electrophoresis with laser-induced fluorescence detection

A new capillary electrophoresis (CE) method with laser-induced fluorescence (LIF) detection was developed for the rapid separation and sensitive detection of glutathione (GSH) and glutathione disulfide (GSSH) after derivatization by 4-chloro-7-nitrobenzo-2-oxa-1,3-diazol (NBD-Cl). The derivatization and separation conditions were investigated in detail and the optimums were obtained. Under the optimum experiment conditions, linear relationships between the peak height and concentrations of the analytes in normal and second-derivative electrophoregrams were obtained (0.22-45.00muM). The detection limits for glutathione and glutathione disulfide in normal and second-derivative electrophoregrams were 0.046 and 0.012muM and 0.046 and 0.014muM, respectively. The method was applied to the analysis of glutathione and glutathione disulfide in human plasma and tobacco leaves with satisfactory results.

2-Mercaptobenzothiazole-bonded silica gel as selective adsorbent for preconcentration of gold, platinum and palladium prior to their simultaneous inductively coupled plasma optical emission spectrometric determination

A 2-mercaptobenzothiazole-bonded silica gel chelating adsorbent(MBTSG) was synthesised by the Mannich reaction between 2-mercaptobenzothiazole and aminopropyl silica gel, and its adsorption characteristics were studied in detail. AuIII, PtIV and PdII can be quantitatively adsorbed by the adsorbent from aqueous solution at pH≤5.0 and CH+≤6 M. The adsorption capacities of AuIII, PtIV and PdII were >4.5, >6.5 and >18 mg per gram of dry MBTSG, respectively. The adsorbed metal ions can be readily desorbed with 3% thiourea in 3 M HCl solution. Other metal ions caused little interference in the preconcentration and simultaneous determination of AuIII, PtIV and PdII by ICP-OES. Concentrations of 2 ppb of Au, Pt and Pd can be determined reliably with a preconcentration factor of 250.

Application of 1-alkyl-3-methylimidazolium-based ionic liquids as background electrolyte in capillary zone electrophoresis for the simultaneous determination of five anthraquinones in Rhubarb

A capillary zone electrophoresis method using only 1-alkyl-3-methylimidazolium-based ionic liquids as background electrolyte for the simultaneous determination of five anthraquinone derivatives including aloe-emodin, emodin, chrysophanol, physcion and rhein in Rhubarb species was described. Ion association constants, K(ass), between anthraquinone anions and imidazolium cations were determined by analyzing the electrophoretic mobility change of anthraquinone anions using a non-linear least-squares method and factors contributing to ion associability were systematically clarified. For method optimization, several parameters such as ionic liquids concentration, background electrolyte pH and applied voltage, on the separation were evaluated and the optimum conditions were obtained as follows: 90mM 1-butyl-3-methylimidazolium tetrafluoroborate (pH 11.0) with an applied voltage of 20kV. Under these conditions, the method has been successfully applied to the determination of anthraquinones in extracts of two kinds of Rhubarb plants (R. palmatum and R. hotaoense) within 12min. The method proposed herein was shown to be much simpler than the previously reported methods.